AlphaFold and protein structure prediction
Demis HassabisJohn JumperDavid Baker
This page delivers no verdict; it presents claims and evidence with their sources. No theory in science is absolute. Method
For everyone
Predicting a protein's three-dimensional shape from its amino-acid sequence was a 50-year-old problem in biology. AlphaFold 2 made predictions close to experimental accuracy at the CASP competition in 2020. Hassabis, Jumper and David Baker received the 2024 Nobel Prize in Chemistry. The predictions remain models that need experimental confirmation.
For specialists
AlphaFold 2 learns inter-residue relationships with multiple sequence alignments and "Evoformer" attention blocks, and its structure module produces atomic coordinates end to end. The median GDT_TS at CASP14 was about 92.4. The model is less reliable for disordered regions, multiple conformations and the effects of mutations; prediction confidence is reported as a pLDDT score.
Claims
- A protein's 3D structure can in most cases be predicted from its amino-acid sequence with near-experimental accuracy.[1]
Evidence
Supporting
In the blind assessment CASP14, most predictions matched experimental structures to near-atomic accuracy.[1]
Challenging
It was stressed that predicted structures may not substitute for experimental ones in drug design and in understanding conformational change.[2]
Connections
Sources
- Article (2021). Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589DOI 10.1038/s41586-021-03819-2archive
- Article (2024). AlphaFold predictions are valuable hypotheses and accelerate but do not replace experimental structure determination. Nature Methods 21, 110–116DOI 10.1038/s41592-023-02087-4archive
Search the literature
Look for scholarly work on this topic in other indexes:
Cite this page
Athena contributors. (2026). AlphaFold and protein structure prediction. Athena: The tree of human knowledge. Retrieved November 1, 2026, from https://latifkedi.github.io/athena/en/d/alphafold/
@misc{athena_alphafold,
title = {AlphaFold and protein structure prediction},
author = {{Athena contributors}},
year = {2026},
howpublished = {\url{https://latifkedi.github.io/athena/en/d/alphafold/}},
note = {Athena: The tree of human knowledge. Accessed: 2026-11-01}
}Added: September 27, 2026 · Last changed: September 28, 2026 · Page history